He Zhu

Publication Activity (10 Years)

Years Active: 2009-2024
Publications (10 Years): 22

Top Topics

Reinforcement Learning

Provably Correct

Control Structures

Top Venues

Publications

Yuning Wang, He Zhu
Safe Exploration in Reinforcement Learning by Reachability Analysis over Learned Models. CAV (3) (2024)
Guofeng Cui, Yuning Wang, Wenjie Qiu, He Zhu
Reward-Guided Synthesis of Intelligent Agents with Control Structures. Proc. ACM Program. Lang. 8 (PLDI) (2024)
Ziheng Chen, Fabrizio Silvestri, Gabriele Tolomei, Jia Wang, He Zhu, Hongshik Ahn
Explain the Explainer: Interpreting Model-Agnostic Counterfactual Explanations of a Deep Reinforcement Learning Agent. IEEE Trans. Artif. Intell. 5 (4) (2024)
Wenjie Qiu, Wensen Mao, He Zhu
Instructing Goal-Conditioned Reinforcement Learning Agents with Temporal Logic Objectives. NeurIPS (2023)
Yuning Wang, He Zhu
Verification-guided Programmatic Controller Synthesis. TACAS (2) (2023)
Wenjie Qiu, He Zhu
Programmatic Reinforcement Learning without Oracles. ICLR (2022)
Hanxiong Chen, Yunqi Li, He Zhu, Yongfeng Zhang
Learn Basic Skills and Reuse: Modularized Adaptive Neural Architecture Search (MANAS). CIKM (2022)
Hanxiong Chen, Yunqi Li, He Zhu, Yongfeng Zhang
Learn Basic Skills and Reuse: Modularized Adaptive Neural Architecture Search (MANAS). CoRR (2022)
Zikang Xiong, Joe Eappen, He Zhu, Suresh Jagannathan
Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising. ECML/PKDD (3) (2022)
Ziheng Chen, Fabrizio Silvestri, Jia Wang, He Zhu, Hongshik Ahn, Gabriele Tolomei
ReLAX: Reinforcement Learning Agent Explainer for Arbitrary Predictive Models. CIKM (2022)
Zikang Xiong, Joe Eappen, He Zhu, Suresh Jagannathan
Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising. CoRR (2022)
Guofeng Cui, He Zhu
Differentiable Synthesis of Program Architectures. NeurIPS (2021)
Zikang Xiong, Joe Eappen, He Zhu, Suresh Jagannathan
Robustness to Adversarial Attacks in Learning-Enabled Controllers. CoRR (2020)
Xuankang Lin, He Zhu, Roopsha Samanta, Suresh Jagannathan
Art: Abstraction Refinement-Guided Training for Provably Correct Neural Networks. FMCAD (2020)
He Zhu, Zikang Xiong, Stephen Magill, Suresh Jagannathan
An inductive synthesis framework for verifiable reinforcement learning. PLDI (2019)
Xuankang Lin, He Zhu, Roopsha Samanta, Suresh Jagannathan
ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks. CoRR (2019)
He Zhu, Zikang Xiong, Stephen Magill, Suresh Jagannathan
An Inductive Synthesis Framework for Verifiable Reinforcement Learning. CoRR (2019)
He Zhu, Stephen Magill, Suresh Jagannathan
A data-driven CHC solver. PLDI (2018)
He Zhu, Gustavo Petri, Suresh Jagannathan
Automatically learning shape specifications. PLDI (2016)
He Zhu, Aditya V. Nori, Suresh Jagannathan
Dependent Array Type Inference from Tests. VMCAI (2015)
He Zhu, Aditya V. Nori, Suresh Jagannathan
Learning refinement types. ICFP (2015)
He Zhu, Gustavo Petri, Suresh Jagannathan
Poling: SMT Aided Linearizability Proofs. CAV (2) (2015)
He Zhu, Suresh Jagannathan
Compositional and Lightweight Dependent Type Inference for ML. VMCAI (2013)
Fei He, He Zhu, William N. N. Hung, Xiaoyu Song, Ming Gu
Compositional Abstraction Refinement for Timed Systems. TASE (2010)
He Zhu, Fei He, William N. N. Hung, Xiaoyu Song, Ming Gu
Data mining based decomposition for assume-guarantee reasoning. FMCAD (2009)